Intelligent control system and method for ultrahigh-temperature instantaneous steam sterilization equipment

Abstract

The invention belongs to the technical field of equipment control, and discloses an intelligent control system and method for ultrahigh-temperature instantaneous steam sterilization equipment. The method comprises the steps of receiving food raw material data collected by an analysis end; analyzing the food raw material data to obtain a food surface area; optimizing equipment parameters of the sterilization equipment according to the food raw material data and the food surface area to obtain optimal equipment parameters; collecting parameter influence data; calculating a parameter deviation value according to the parameter influence data, and correcting the optimal equipment parameters according to the parameter deviation value; the sterilization equipment is controlled to operate according to the corrected optimal equipment parameters; performing sterilization effect evaluation on the sterilized food, optimizing a preset feeding amount according to the sterilization effect, and sending the optimized feeding amount to an analysis end; automatic control of the sterilization equipment is achieved, invalid sterilization caused by excessive energy waste is avoided, and the sterilization effect and the energy utilization efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment control, and more specifically, to an intelligent control system and method for an ultra-high temperature instantaneous steam sterilization device. Background Art

[0002] Chinese Patent No. CN212087934U discloses an ultra-high temperature instantaneous food material sterilizer, which includes a high-temperature sterilization tank, a heat exchanger, and a heating pipeline. The high-temperature sterilization tank is of a cylindrical structure. The heat exchanger is arranged on one side of the high-temperature sterilization tank, and the heat exchanger is connected to the high-temperature sterilization tank through a discharge transition pipeline and a feed transition pipeline. The heating pipeline is arranged inside the high-temperature sterilization tank, and the heating pipeline is connected to the high-temperature sterilization tank by welding. The steam input pipeline is arranged on one side of the high-temperature sterilization tank, and the steam input pipeline is connected to the high-temperature sterilization tank by welding. The steam output pipeline is arranged on the top of the high-temperature sterilization tank. This device has the advantages of simple structure, convenient maintenance, fast heating speed, and high working efficiency.

[0003] Although the above technology can be used in the food sterilization process, it cannot adjust various parameters of the sterilization equipment in real time during the food sterilization process, such as steam temperature, feed rate, etc. In the food production line, due to various factors such as the raw material characteristics of food (such as the surface area, moisture content of food, etc.), environmental conditions (such as environmental temperature and humidity, etc.), and feed volume, etc., all change. Therefore, during the process of sterilizing food, in order to achieve the best sterilization effect, the actual requirements for various parameters of the sterilization equipment are also different. If various parameters cannot be adjusted in real time, it is difficult to ensure the stability of food sterilization quality, and it will cause a certain degree of energy waste, thus reducing the energy utilization efficiency of the sterilization equipment.

[0004] In view of this, the present invention proposes an intelligent control system and method for an ultra-high temperature instantaneous steam sterilization device to solve the above problems. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art and achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent control method for an ultra-high temperature instantaneous steam sterilization device includes:

[0007] Receiving food raw material data collected by an analysis terminal;

[0008] Analyzing the food raw material data to obtain the food surface area;

[0009] Optimizing the equipment parameters of the sterilization equipment according to the food raw material data and the food surface area to obtain the optimal equipment parameters;

[0010] The acquisition parameters affect the data;

[0011] According to the parameters affecting the data, calculate the parameter deviation amount, and correct the optimal equipment parameters according to the parameter deviation amount; and control the sterilization equipment to operate according to the corrected optimal equipment parameters;

[0012] Evaluate the sterilization effect of the food after sterilization, optimize the preset feeding amount according to the sterilization effect, and send the optimized feeding amount to the analysis terminal.

[0013] Furthermore, the food raw material data includes microbial contamination degree, moisture content, and food images;

[0014] The method for obtaining the food surface area includes:

[0015] Perform grayscale processing on the food image in the food raw material data to obtain the grayscale values of a pixel points, where a is the total number of pixel points in the food image;

[0016] Preset a grayscale value threshold, compare and analyze the grayscale values of the a pixel points with the grayscale value threshold respectively, mark the pixel points with grayscale values less than or equal to the grayscale value threshold as food points, and do not mark the pixel points with grayscale values greater than the grayscale value threshold;

[0017] Extract the attributes of the food image from the food image, obtain the resolution of the food image according to the attributes of the food image, and then obtain the area of a pixel point according to the resolution of the food image; preset a scaling factor, and count the number of food points, and multiply the number of food points, the scaling factor, and the area of a pixel point in sequence to obtain the food surface area.

[0018] Furthermore, the equipment parameters include steam temperature and feeding speed;

[0019] The method for obtaining the optimal equipment parameters includes:

[0020] Initialize the temperature T max , the lowest temperature T min , the cooling coefficient δ, the maximum number of iterations and m parameter sets, where m is an integer greater than 1, randomly generate available solutions and define a fitness function; generate a new available solution χ′ by perturbing in the neighborhood through cyclic iteration, and decide whether to accept the new available solution according to the fitness difference (adopt the better solution directly, and accept the worse solution with a certain probability). After completing one iteration, reduce the current temperature and reset the maximum number of iterations, and repeat this process until the temperature drops to the lowest temperature T min , and finally output the parameter set corresponding to the available solution with the optimal fitness as the set corresponding to the optimal equipment parameters.

[0021] Further, in the method for obtaining the optimal equipment parameters, a preset parameter range is set, and the parameter range includes a steam temperature range and a feed rate range; a value is randomly selected from the steam temperature range and the feed rate range respectively, and a parameter set is constructed. A total of m parameter sets are constructed, and the m parameter sets are all different;

[0022] The fitness difference f″ is obtained by calculating the difference between the fitness f′ corresponding to the new available solution χ′ and the fitness f corresponding to the available solution χ.

[0023] Further, in the method for obtaining the optimal equipment parameters, the value of the fitness function is the residual contamination degree;

[0024] The residual contamination degree is the average contamination degree of the microorganisms remaining after sterilization in the foods sterilized in the same batch; the method for obtaining the residual contamination degree includes:

[0025] Obtain the sterilization distance, where the sterilization distance is the distance between the inlet and the outlet in the sterilization equipment; divide the sterilization distance by the feed rate corresponding to the available solution χ to obtain the sterilization duration; use the analysis data, the sterilization duration, and the steam temperature as test data, and input the test data into the trained pollution prediction model to predict the corresponding residual contamination degree; the analysis data includes the microbial contamination degree, the moisture content, and the food surface area.

[0026] The training process of the pollution prediction model includes:

[0027] Pre-collect b groups of test data, and set corresponding residual contamination degrees for the b groups of test data, where b is an integer greater than 1. Convert the test data and the corresponding residual contamination degrees into a corresponding set of feature vectors; use each set of feature vectors as the input of the pollution prediction model. The pollution prediction model takes the predicted residual contamination degree corresponding to each group of test data as the output, and takes the actual residual contamination degree corresponding to each group of test data as the prediction target. The actual residual contamination degree is the residual contamination degree pre-collected corresponding to the test data; use minimizing the sum of the prediction errors of all test data as the training target; train the pollution prediction model until the sum of the prediction errors reaches convergence and then stop training; the pollution prediction model is a deep neural network model.

[0028] Further, the parameter influence data includes environmental influence data and power difference; the environmental influence data includes environmental temperature and environmental humidity;

[0029] The method for obtaining the power difference is: continuously collect the historical power differences at c time points, where c is an integer greater than 1; train a difference prediction model based on the c historical power differences; input the c historical power differences into the trained difference prediction model to predict the power difference at the current time point.

[0030] Further, the method for calculating the parameter deviation amount includes:

[0031] Input the parameter influence data into the trained deviation analysis model to calculate the corresponding parameter deviation amount; the training process of the deviation analysis model is the same as that of the pollution prediction model, and both are deep neural network models; the parameter deviation amount is the steam temperature deviation amount. Add the parameter deviation amount to the steam temperature in the optimal equipment parameters to obtain the steam temperature correction amount, and correct the steam temperature in the optimal equipment parameters to the steam temperature correction amount.

[0032] Further, the method for evaluating the sterilization effect of the food after sterilization includes:

[0033] Collect the microbial contamination degree of the food after sterilization and label it as the remaining contamination degree; divide the remaining contamination degree by the microbial contamination degree to obtain the sterilization effect.

[0034] The method for optimizing the preset feeding amount according to the sterilization effect includes:

[0035] The feeding amount is the weight corresponding to the food sterilized in the same batch; preset an effect threshold and compare the sterilization effect with the effect threshold; if the sterilization effect is less than the effect threshold, generate an optimization instruction; if the sterilization effect is greater than or equal to the effect threshold, do not generate an optimization instruction; preset a proportionality coefficient. If an optimization instruction is generated, multiply the proportionality coefficient by the sterilization effect to obtain the optimization ratio, and multiply the preset feeding amount by the optimization ratio to obtain the optimized feeding amount.

[0036] Further, it also includes: collecting the distance to be sterilized and calculating the heating time, and adjusting the feeding speed according to the distance to be sterilized and the heating time;

[0037] The distance to be sterilized is the distance between the food to be sterilized in the next batch and the entrance of the sterilization equipment;

[0038] The method for calculating the heating time includes:

[0039] Obtain the steam quality and the specific heat capacity of the steam; collect the current temperature of the steam; subtract the current temperature of the steam from the steam temperature in the optimal equipment parameters to obtain the temperature to be increased of the steam; obtain the actual heating power at the current time point and label it as the current power; multiply the steam quality, the specific heat capacity of the steam, and the temperature to be increased of the steam in sequence, and then divide by the current power to obtain the heating time.

[0040] Divide the distance to be sterilized by the heating time to obtain the optimal feeding speed; control the sterilization equipment to operate according to the optimal feeding speed.

[0041] An intelligent control system for an ultra-high temperature instantaneous steam sterilization device, implementing the intelligent control method for an ultra-high temperature instantaneous steam sterilization device, includes:

[0042] A data receiving module for receiving food raw material data collected by an analysis terminal;

[0043] A data analysis module for analyzing the food raw material data to obtain the food surface area;

[0044] A parameter optimization module for optimizing the equipment parameters of a sterilization device according to the food raw material data and the food surface area to obtain the optimal equipment parameters;

[0045] A data collection module for collecting parameter influence data;

[0046] A parameter correction module for calculating a parameter deviation amount according to the parameter influence data, correcting the optimal equipment parameters according to the parameter deviation amount; and controlling the sterilization device to operate according to the corrected optimal equipment parameters;

[0047] An effect evaluation module for evaluating the sterilization effect of the food after sterilization is completed, optimizing a preset feeding amount according to the sterilization effect, and sending the optimized feeding amount to the analysis terminal.

[0048] The technical effects and advantages of an intelligent control system and method for an ultra-high temperature instantaneous steam sterilization device of the present invention:

[0049] 1. By collecting and analyzing food raw material data in real time, accurately obtaining the food surface area, and realizing dynamic optimization of parameters using the simulated annealing algorithm according to the raw material data and surface area; at the same time, collecting parameter influence data and using a deep learning algorithm to correct parameters in real time, thereby realizing full-process intelligent control of the sterilization device parameters; in addition, optimizing the feeding amount according to the evaluation results of the sterilization effect, further improving the control parameters of the sterilization device; having the advantages of instantaneous response and automatic adaptation to the characteristics of different raw materials and influencing parameters, thereby realizing automatic control of the sterilization device, avoiding wasting too much energy for ineffective sterilization, and then ensuring the food sterilization quality, improving the sterilization effect and energy utilization efficiency.

[0050] 2. Dynamically calculate the optimal feeding speed according to the distance to be sterilized before different batches of food enter the sterilization device and the time required for heating steam; neither prevent the feeding speed from being too fast, resulting in the food entering the sterilization device before the steam is heated to the optimal steam temperature, affecting the sterilization effect; nor avoid the feeding speed from being too slow, affecting the production efficiency; through the optimized control of the feeding speed, accurate control of the sterilization temperature and intelligent optimization of the process are realized, not only improving the sterilization effect, but also effectively saving energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic diagram of an intelligent control system for an ultra-high temperature instantaneous steam sterilization device according to Embodiment 1 of the present invention;

[0052] Figure 2 Schematic diagram of the position of the analysis terminal and the sterilization equipment in Embodiment 1 of the present invention;

[0053] Figure 3 Schematic diagram of the intelligent control system of an ultra-high temperature instantaneous steam sterilization equipment in Embodiment 2 of the present invention;

[0054] Figure 4 Flowchart of the intelligent control method of an ultra-high temperature instantaneous steam sterilization equipment in Embodiment 3 of the present invention. Specific embodiments

[0055] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0056] Embodiment 1

[0057] Please refer to Figure 1 As shown, the intelligent control system of an ultra-high temperature instantaneous steam sterilization equipment in this embodiment includes a data receiving module, a data analysis module, a parameter optimization module, a data acquisition module, a parameter correction module, and an effect evaluation module; each module is connected by wired and / or wireless means to achieve data transmission between modules.

[0058] The data receiving module is used to receive the food raw material data collected by the analysis terminal, such as agricultural products like fruits, vegetables, and gastrodia elata.

[0059] The analysis terminal includes a feeding device and an analysis device; the feeding device is a device for transporting food from the storage bin to the production line, and the analysis device is a device for analyzing food raw material data; the positional relationship between the analysis terminal and the sterilization equipment is as Figure 2 shown, and the sterilization equipment is the ultra-high temperature instantaneous steam sterilization equipment; the analysis device includes a microbial contamination detector, an infrared moisture meter, and an image sensor.

[0060] The food raw material data includes microbial contamination, moisture content, and food images; the microbial contamination is the average contamination degree of microorganisms in the food sterilized in the same batch; the moisture content is the average moisture content corresponding to the food sterilized in the same batch; among them, the microbial contamination is obtained by the microbial contamination detector, the moisture content is obtained by the infrared moisture meter, and the food image is obtained by the image sensor.

[0061] The higher the microbial contamination level, the more microbial contamination exists in the food of the same batch. Therefore, it is necessary to increase the steam temperature to completely kill the existing microorganisms. At the same time, it is necessary to reduce the feeding speed to extend the sterilization time of the food of the same batch and ensure that the food of the same batch is fully sterilized at ultra-high temperature. The higher the moisture content, the more free water molecules there are inside the food of the same batch, which will reduce the heat conduction efficiency. Therefore, it is necessary to increase the steam temperature to ensure that the inside of the food of the same batch can reach a sufficient sterilization temperature. At the same time, it is also necessary to slow down the feeding speed to extend the sterilization time and ensure that the food of the same batch is fully heated at ultra-high temperature.

[0062] It should be noted that since multiple foods can be sterilized simultaneously each time during food production to improve the sterilization efficiency, and the foods sterilized simultaneously are the foods of the same batch, the microbial contamination level and moisture content in the food raw material data are both the averages of multiple foods to accurately reflect the overall situation of the foods sterilized in the same batch.

[0063] The data analysis module is used to analyze the food raw material data to obtain the food surface area.

[0064] The methods for obtaining the food surface area include:

[0065] Perform grayscale processing on the food image in the food raw material data to obtain the grayscale values of a pixel points, where a is the total number of pixel points in the food image;

[0066] Preset a grayscale value threshold, compare and analyze the grayscale values of the a pixel points with the grayscale value threshold respectively, mark the pixel points with grayscale values less than or equal to the grayscale value threshold as food points, and do not mark the pixel points with grayscale values greater than the grayscale value threshold.

[0067] It should be noted that the grayscale value threshold is obtained by those skilled in the art during the historical food sterilization process. Multiple food images are collected and grayscale processed, and the grayscale values of the pixels corresponding to the food in one food image are used as a grayscale value set; the maximum grayscale value in each grayscale value set is obtained and marked as the maximum grayscale value; the average value of multiple maximum grayscale values is used as the grayscale value threshold.

[0068] It should be understood that since the color of the food itself is relatively light, usually yellow or grayish-brown, and the production line equipment is usually made of metal with a darker color, such as black, dark gray, etc.; after grayscale processing, the darker color corresponds to a higher grayscale value, while the lighter color corresponds to a lower grayscale value. Therefore, the pixel values of the pixels corresponding to the food in the food image will be lower than the grayscale values of the pixels corresponding to the production line equipment.

[0069] Extract the attributes of a food image from the food image, obtain the resolution of the food image based on the attributes of the food image, and then obtain the area of a pixel point based on the resolution of the food image; preset a scaling factor, and count the number of food points. Multiply the number of food points, the scaling factor, and the area of a pixel point in sequence to obtain the food surface area; the scaling factor is measured by those skilled in the art for the food surface area corresponding to multiple food images and the actual food surface area when determining the grayscale value threshold. The food surface area in the food image is the measured food surface area in the food image, and the actual food surface area is the measured food surface area on-site. Divide the actual food surface area by the food surface area in the food image to obtain the surface area ratio, and take the average value of multiple surface area ratios as the scaling factor.

[0070] Expression for food surface area: M = TS × TM × λ;

[0071] In the formula, M is the food surface area, TS is the number of food points, TM is the area of a pixel point, and λ is the scaling factor.

[0072] The larger the food surface area, the larger the area where steam can come into contact and transfer heat, which means that with the same heat input, the food can be heated to the required sterilization temperature faster. Therefore, the required steam temperature is lower, and the feeding speed is higher to reduce the sterilization time, improve the sterilization efficiency, and ensure the sterilization quality while doing so.

[0073] A parameter optimization module, used to optimize the equipment parameters of the sterilization equipment according to the food raw material data and the food surface area, and obtain the optimal equipment parameters.

[0074] The equipment parameters include steam temperature and feeding speed;

[0075] The steam temperature is the temperature of the steam for sterilizing the food. The steam temperature will directly affect the sterilization effect of the food. If the steam temperature is too low, the sterilization temperature cannot be reached, thus reducing the sterilization effect. If the temperature is too high, it will cause energy waste, reduce the energy utilization efficiency, and may even damage the quality of the food;

[0076] The feeding speed is the speed at which the food enters the sterilization equipment; the feeding speed determines the residence time of the food in the sterilization equipment, that is, it determines the actual sterilization time; if the feeding speed is too fast, the food cannot fully absorb the required heat, thus reducing the sterilization effect, and if the feeding speed is too slow, it will reduce the production efficiency, increase the energy consumption, and reduce the energy utilization efficiency.

[0077] The method for obtaining the optimal equipment parameters includes:

[0078] Initialize the temperature T max 、the lowest temperature T min 、the cooling coefficient δ, the maximum number of iterations and m sets of parameters, where m is an integer greater than 1. Randomly generate available solutions and define a fitness function. Through iterative loops, perturb in the neighborhood to generate a new available solution χ′, and decide whether to accept the new available solution based on the fitness difference (adopt the better solution directly and accept the worse solution with a certain probability). After one round of iteration, reduce the current temperature and reset the maximum number of iterations, and repeat the iterative process until the temperature drops to the lowest temperature T min , and finally output the set of parameters corresponding to the available solution with the best fitness as the set corresponding to the best device parameters. The specific steps are as follows:

[0079] Step a: Preset the initial temperature T max , the lowest temperature T min , the temperature reduction coefficient δ, the maximum number of iterations and m sets of parameters, and let the current temperature T = T max , where m is an integer greater than 1;

[0080] Step b: Randomly set an available solution χ. The available solution χ is the set of parameters, and the range of the available solution χ is the m sets of parameters;

[0081] Step c: Determine the fitness function;

[0082] Step d: Calculate the fitness f corresponding to the available solution χ. Taking the available solution χ as the current point, perform random perturbation in the neighborhood of the current point to obtain a new available solution χ′, and calculate the fitness f′ corresponding to the new available solution χ′;

[0083] Step e: Calculate the fitness difference f″. If the fitness difference f″ > 0, then let χ = χ′; if the fitness difference f″ ≤ 0, then calculate the probability p′, and let χ = χ′ according to the probability p′;

[0084] Step f: Loop steps d to e until the number of loops reaches the maximum number of iterations when the loop ends and enter step g;

[0085] Step g: Let the current temperature T = T × δ, that is, cool down the current temperature in step a, and assign the cooled value to the current temperature; let the maximum number of iterations that is, assign the reduced value of the maximum number of iterations to the maximum number of iterations; if the reduced maximum number of iterations is not an integer, then round up the reduced maximum number of iterations to make the reduced maximum number of iterations an integer;

[0086] Step h: Loop steps d to g until the current temperature T < T min when the loop ends, obtain the set of parameters corresponding to the available solution χ and use it as the set corresponding to the best device parameters.

[0087] It should be noted that the initial temperature T max , the lowest temperature T min , the cooling coefficient δ, and the maximum number of iterations are used as preset parameters. The preset parameters are obtained by those skilled in the art from multiple sets of different analysis data during the historical food sterilization process. The analysis data includes the degree of microbial contamination, moisture content, and food surface area. For a batch of foods with the same analysis data, multiple sets of different preset parameters are sequentially preset, and the simulated annealing algorithm is sequentially used to obtain parameter sets. According to the obtained multiple sets of parameter sets, the corresponding fitness is obtained; the preset parameters corresponding to the parameter set with the maximum fitness are used as the preset parameters corresponding to this set of test data, and so on to obtain the preset parameters corresponding to multiple sets of different test data. The average values of multiple preset parameters (i.e., the average value of the initial temperature, the average value of the lowest temperature, the average value of the cooling coefficient, and the average value of the maximum number of iterations) are used as the preset initial temperature T max , the lowest temperature T min , the cooling coefficient δ, and the maximum number of iterations

[0088] In the above step a, a preset parameter range is included. The parameter range includes the steam temperature range and the feed rate range; the parameter range is set by those skilled in the art during the historical food sterilization process by collecting the corresponding steam temperature and feed rate multiple times. According to the minimum and maximum steam temperatures collected, the steam temperature range is set, and according to the minimum and maximum feed rates collected, the feed rate range is set; a value is randomly selected from the steam temperature range and the feed rate range respectively, and a parameter set is constructed, that is, a parameter set includes a steam temperature and a feed rate, and a total of m parameter sets are constructed, and the m parameter sets are all different.

[0089] In the above step c, the expression of the fitness function is: f = ww;

[0090] In the formula, f is the fitness, and ww is the residual contamination degree;

[0091] The residual contamination degree is the average contamination degree of the microorganisms remaining after sterilization in the foods sterilized in the same batch.

[0092] The method for obtaining the residual contamination degree includes:

[0093] Obtain the sterilization distance. The sterilization distance is the distance between the inlet and the outlet in the sterilization equipment; the sterilization distance is obtained by those skilled in the art by measuring the sterilization equipment; divide the sterilization distance by the feed rate corresponding to the available solution χ to obtain the sterilization duration; use the analysis data, the sterilization duration, and the steam temperature as test data, and input the test data into the trained pollution prediction model to predict the corresponding residual contamination degree;

[0094] The specific training process of the pollution prediction model includes:

[0095] Pre-collect b groups of test data, set corresponding residual pollution degrees for the b groups of test data, where b is an integer greater than 1, and convert the test data and the corresponding residual pollution degrees into a corresponding set of feature vectors; the residual pollution degrees corresponding to the test data are collected by those skilled in the art during the historical food sterilization process. For the b groups of test data, under the analysis data conditions of each group of test data, using a sterilization device with the steam temperature adjusted to the steam temperature in the test data, after the sterilization process with the sterilization duration in the test data, use a microbial pollution detector to collect the microbial pollution degree again and use it as the residual pollution degree; set the corresponding residual pollution degrees for the b groups of test data in sequence;

[0096] Take each group of feature vectors as the input of the pollution prediction model. The pollution prediction model takes the predicted residual pollution degree corresponding to each group of test data as the output, takes the actual residual pollution degree corresponding to each group of test data as the prediction target, and the actual residual pollution degree is the residual pollution degree corresponding to the pre-collected test data; take minimizing the sum of the prediction errors of all test data as the training target; among them, the calculation formula of the prediction error is η K =(β K -ε K ) 2 , where η K is the prediction error, K is the group number of the feature vector corresponding to the test data, β K is the predicted residual pollution degree corresponding to the Kth group of test data, and ε K is the actual residual pollution degree corresponding to the Kth group of test data; train the pollution prediction model until the sum of the prediction errors reaches convergence and then stop training.

[0097] It should be noted that using a deep neural network can learn complex non-linear relationships, can accurately capture the influence of the sterilization duration and steam temperature on the residual pollution degree under the analysis data conditions, thereby improving the prediction accuracy; and the deep neural network can automatically learn effective feature representations from the original data, reducing the modeling difficulty; at the same time, the deep neural network model has a certain fault tolerance ability, can still give reliable prediction results in the case of noise or missing data, and improve the prediction accuracy of the residual pollution degree of food in the actual production line; in addition, as more data is collected and fed back, the deep neural network model can continuously perform re-training and optimization, continuously improving the prediction performance.

[0098] In the above step e, the expression of the fitness difference f″ is f″ = f′ - f; let χ = χ′, that is, assign the value of the new available solution χ′ to the available solution χ; the expression of the probability p′ is: In the formula, e is the natural constant; according to the probability p′, let χ = χ′, that is, the probability of χ = χ′ is p′; the operation adopted in step e is roulette wheel selection, and the probability of each available solution being selected is determined according to its fitness, so as to retain excellent available solutions and eliminate poor available solutions; and the available solutions with lower fitness are not directly eliminated to avoid premature convergence of the algorithm, and can continue to explore the new solution space, increasing the chance of finding the global optimal solution.

[0099] It should be understood that the reason for using the simulated annealing algorithm to obtain the optimal device parameters is that the simulated annealing algorithm can automatically optimize the device parameters to obtain the best sterilization effect and improve the automation degree of the device; and the simulated annealing algorithm can gradually converge to the optimal solution based on a certain degree of randomness, with good global search ability, avoiding falling into the local optimal solution; at the same time, the algorithm parameters such as the initial temperature and the cooling coefficient can be flexibly set to adapt to the characteristics of different sterilization devices and food raw materials, improving the adaptability and robustness of the simulated annealing algorithm.

[0100] The data acquisition module is used to acquire the parameter influence data.

[0101] The parameter influence data includes environmental influence data and power difference;

[0102] The environmental influence data includes environmental temperature and environmental humidity; the environmental temperature is obtained by a temperature sensor installed on the sterilization device; the environmental humidity is obtained by a humidity sensor installed on the sterilization device; the lower the environmental temperature, the more heat loss is generated during the transmission of steam, so the steam temperature is lower, and vice versa; when the environmental humidity is higher, the steam is more likely to condense during the transmission process, and the steam condensation will cause the steam temperature to drop, so the steam temperature is lower;

[0103] The power difference is the difference between the set heating power and the actual heating power of the heating system in the sterilization device; the method for obtaining the power difference is as follows: continuously collect the historical power differences at c time points, where c is an integer greater than 1; the historical power differences at c time points are obtained by those skilled in the art during the historical food sterilization process, subtracting the collected corresponding actual heating power from the set heating power at c time points to obtain the historical power differences at c time points; the time difference between every two time points is a preset time point, and the time point is preset by those skilled in the art according to the actual situation; train the difference prediction model according to the c historical power differences; input the c historical power differences into the trained difference prediction model to predict the power difference at the current time point; the larger the power difference, the more the performance of the heating system in the sterilization device decreases, and the temperature rise is blocked, resulting in the actual steam temperature not reaching the set steam temperature and the steam temperature decreasing.

[0104] The training method of the difference prediction model adopts a dynamic time series analysis strategy, and the specific steps are as follows:

[0105] Data preprocessing stage:

[0106] Construct a basic training data set based on the historical power differences at consecutive c time points to form an input matrix with time series characteristics.

[0107] Sample generation strategy:

[0108] Use the sliding window technique (window length is W, step size is L) to dynamically segment the power differences in the basic training data set to generate a training sample group containing context information. Each sample contains the power differences at the first W time points as input features, and the power differences corresponding to L steps later as the prediction target.

[0109] Model architecture design:

[0110] Adopt a recurrent neural network (RNN) as the core prediction model, and utilize its memory characteristics for time series data to capture the dynamic change law of power differences. The dimension of the input layer matches the window length, and the dimension of the output layer corresponds to the single-step prediction target.

[0111] Training and optimization process:

[0112] Take the prediction accuracy as the optimization goal, and adopt the mean absolute percentage error (MAPE) as the model performance evaluation index. Optimize the network parameters through the backpropagation algorithm, and terminate the training when the measured MAPE value is lower than the preset threshold.

[0113] Model verification mechanism:

[0114] After training, a difference prediction model with time series prediction ability is generated, which can output the prediction results of the power differences in the next L steps based on the input historical difference sequence.

[0115] This method enhances the data utilization rate through the dynamic window mechanism, combines the time series modeling advantages of RNN, and realizes the accurate prediction of power differences.

[0116] It should be noted that as the usage time of the sterilization equipment increases, the components inside the equipment will gradually age and wear, and the control system inside the equipment will also gradually drift, resulting in an increase in power differences as the usage time of the sterilization equipment increases; the RNN model can effectively capture the dynamic patterns in time series data and is more suitable for dealing with problems that change over time such as equipment aging; therefore, an RNN neural network model needs to be adopted to accurately predict the power differences at future time points for subsequent calculation of parameter deviation amounts.

[0117] A parameter correction module is used to calculate a parameter deviation amount based on parameter-influencing data, correct the optimal device parameters according to the parameter deviation amount, and control the sterilization device to operate according to the corrected optimal device parameters.

[0118] The methods for calculating the parameter deviation amount include:

[0119] Input the parameter-influencing data into a trained deviation analysis model to calculate the corresponding parameter deviation amount; the training process of the deviation analysis model is the same as that of the pollution prediction model, and both are deep neural network models; the parameter deviation amount is the steam temperature deviation amount, add the parameter deviation amount to the steam temperature in the optimal device parameters to obtain the steam temperature correction amount, and correct the steam temperature in the optimal device parameters to the steam temperature correction amount.

[0120] An effect evaluation module is used to evaluate the sterilization effect of the food after sterilization, optimize the preset feed rate according to the sterilization effect, and send the optimized feed rate to the analysis terminal.

[0121] The methods for evaluating the sterilization effect of the food after sterilization include:

[0122] Collect the microbial contamination degree of the food after sterilization and mark it as the remaining contamination degree; the remaining contamination degree is obtained by a microbial contamination degree detector installed behind the outlet of the sterilization device; divide the remaining contamination degree by the microbial contamination degree to obtain the sterilization effect.

[0123] The methods for optimizing the preset feed rate according to the sterilization effect include:

[0124] The feed rate is the weight corresponding to the food sterilized in the same batch; the feed rate is preset by those skilled in the art according to the actual situation of the sterilization device; preset an effect threshold, and compare the sterilization effect with the effect threshold; if the sterilization effect is less than the effect threshold, generate an optimization instruction; if the sterilization effect is greater than or equal to the effect threshold, do not generate an optimization instruction; the effect threshold is preset by those skilled in the art according to the required sterilization accuracy requirements; preset a proportionality coefficient, if an optimization instruction is generated, multiply the proportionality coefficient by the sterilization effect to obtain an optimization ratio, multiply the preset feed rate by the optimization ratio to obtain the optimized feed rate; the proportionality coefficient is obtained by those skilled in the art during the historical food sterilization process. When an optimization instruction is generated, adjust the feed rate multiple times and perform sterilization treatment, analyze the corresponding sterilization effect, obtain the adjusted feed rate corresponding to the sterilization effect with the largest value, and mark it as the adjusted feed rate, divide the adjusted feed rate by the feed rate to obtain an adjustment coefficient; and so on to obtain the adjustment coefficients corresponding to multiple generations of optimization instructions, and take the average value of the multiple adjustment coefficients as the proportionality coefficient.

[0125] The feeding rate affects the sterilization effect of food. The larger the feeding rate, the thicker the food will accumulate in the sterilization equipment. However, too thick food will hinder the penetration of ultra-high temperature steam and its full contact with the food, resulting in poor local sterilization effect. Moreover, it will affect the heat transfer and uniform distribution of temperature, causing the temperature of some food to be too low to reach the required sterilization temperature, thus affecting the overall sterilization effect. Therefore, dynamically optimizing the feeding rate according to the sterilization effect feedback after each sterilization can control the feeding rate at a better value, thereby improving the overall sterilization effect of food.

[0126] In this embodiment, by collecting and analyzing food raw material data in real time, the surface area of the food is accurately obtained, and the dynamic optimization of parameters is realized by using the simulated annealing algorithm according to the raw material data and surface area. At the same time, the parameter influence data is collected and the parameters are corrected in real time by using the deep learning algorithm, thus realizing the whole-process intelligent control of the sterilization equipment parameters. In addition, the feeding rate is optimized according to the evaluation result of the sterilization effect, further improving the control parameters of the sterilization equipment. It has the advantages of instantaneous response and automatic adaptation to the characteristics of different raw materials and influencing parameters, thus realizing the automatic control of the sterilization equipment, avoiding wasting too much energy for ineffective sterilization, and then ensuring the food sterilization quality, improving the sterilization effect and energy utilization efficiency.

[0127] Embodiment 2

[0128] As Figure 3 shown, after a batch of food sterilization is completed, the steam inside the sterilization equipment needs to be reheated to meet the sterilization temperature required for the next food sterilization, that is, before the next batch of food enters the sterilization equipment, the steam inside the sterilization equipment needs to be heated to the steam temperature in the optimal equipment parameters. Therefore, this embodiment provides an intelligent control system for an ultra-high temperature instantaneous steam sterilization equipment, which also includes a speed adjustment module.

[0129] The speed adjustment module is used to collect the distance to be sterilized, calculate the heating time, and adjust the feeding speed according to the distance to be sterilized and the heating time.

[0130] The distance to be sterilized is the distance between the next batch of food to be sterilized and the entrance of the sterilization equipment. The distance to be sterilized is obtained by a laser ranging sensor installed on the sterilization equipment, and the laser ranging sensor is parallel to the conveyor belt on the food production line.

[0131] The method for calculating the heating time includes:

[0132] Obtain the steam quality and the specific heat capacity of the steam. The steam quality is obtained by those skilled in the art through measuring the steam, and the specific heat capacity of the steam is obtained according to the steam physical property manual; collect the current temperature of the steam, and the current temperature of the steam is obtained by a temperature sensor such as a thermocouple or an RTD (resistance temperature detector) installed inside the sterilization equipment; subtract the current temperature of the steam from the steam temperature in the optimal equipment parameters to obtain the temperature that the steam needs to rise; obtain the actual heating power at the current time point and mark it as the current power, and the current power is obtained by the control system inside the sterilization equipment; multiply the steam quality, the specific heat capacity of the steam and the temperature that the steam needs to rise in sequence, and then divide by the current power to obtain the heating time.

[0133] Divide the distance to be sterilized by the heating time to obtain the optimal feeding speed; control the sterilization equipment to operate according to the optimal feeding speed.

[0134] In this embodiment, according to the distance to be sterilized before different batches of food enter the sterilization equipment and the time required for the heating steam, the optimal feeding speed is dynamically calculated; it not only prevents the feeding speed from being too fast, resulting in the food entering the sterilization equipment before the steam is heated to the optimal steam temperature and affecting the sterilization effect, but also avoids the feeding speed from being too slow and affecting the production efficiency; through the optimized control of the feeding speed, the precise control of the sterilization temperature and the intelligent optimization of the process are realized, which not only improves the sterilization effect, but also effectively saves energy consumption.

[0135] Embodiment 3

[0136] Please refer to Figure 4 As shown, for the parts not described in detail in this embodiment, refer to the description content of Embodiment 1 and Embodiment 2. A method for intelligent control of an ultra-high temperature instantaneous steam sterilization equipment is provided, and the method includes:

[0137] Receive the food raw material data collected by the analysis terminal;

[0138] Analyze the food raw material data to obtain the food surface area;

[0139] Optimize the equipment parameters of the sterilization equipment according to the food raw material data and the food surface area to obtain the optimal equipment parameters;

[0140] Collect the parameter influence data;

[0141] Calculate the parameter deviation amount according to the parameter influence data, and correct the optimal equipment parameters according to the parameter deviation amount; and control the sterilization equipment to operate according to the corrected optimal equipment parameters;

[0142] Evaluate the sterilization effect of the food after sterilization, optimize the preset feeding amount according to the sterilization effect, and send the optimized feeding amount to the analysis terminal.

[0143] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims described above.

[0144] Finally: The above are only preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent control method for an ultra-high temperature instantaneous steam sterilization device, characterized in that, Including: Receiving the food raw material data collected by the analysis terminal; Analyzing the food raw material data to obtain the food surface area; Optimizing the equipment parameters of the sterilization equipment according to the food raw material data and the food surface area to obtain the optimal equipment parameters; Collecting parameter influence data; Calculating the parameter deviation amount according to the parameter influence data, correcting the optimal equipment parameters according to the parameter deviation amount; and controlling the sterilization equipment to operate according to the corrected optimal equipment parameters; Evaluating the sterilization effect of the food after sterilization, optimizing the preset feeding amount according to the sterilization effect, and sending the optimized feeding amount to the analysis terminal.

2. The intelligent control method of an ultra-high temperature instantaneous steam sterilization device according to claim 1, characterized in that, The food raw material data includes microbial contamination degree, moisture content, and food image; The method for obtaining the food surface area includes: Performing grayscale processing on the food image in the food raw material data to obtain the grayscale values of a pixel points, where a is the number of all pixel points in the food image; Presetting a grayscale value threshold, comparing and analyzing the grayscale values of a pixel points with the grayscale value threshold respectively, marking the pixel points with grayscale values less than or equal to the grayscale value threshold as food points, and not marking the pixel points with grayscale values greater than the grayscale value threshold; Extracting the attributes of the food image from the food image, obtaining the resolution of the food image according to the attributes of the food image, and then obtaining the area of a pixel point according to the resolution of the food image; presetting a scaling factor, and counting the number of food points, multiplying the number of food points, the scaling factor, and the area of a pixel point in sequence to obtain the food surface area.

3. The intelligent control method of an ultra-high temperature instantaneous steam sterilization device according to claim 2, characterized in that, The equipment parameters include steam temperature and feeding speed; the method for obtaining the optimal equipment parameters includes: Initial temperature T max , minimum temperature T min , temperature reduction coefficient δ, maximum number of iterations and m parameter sets, where m is an integer greater than 1. Randomly generate available solutions and define the fitness function; generate a new available solution χ′ by perturbing within the neighborhood through cyclic iteration, and decide whether to accept the new available solution based on the fitness difference. After one iteration, reduce the current temperature and reset the maximum number of iterations, and repeat the iteration process until the temperature drops to the minimum temperature T min , and finally output the parameter set corresponding to the available solution with the optimal fitness as the set corresponding to the best device parameters.

4. The intelligent control method of an ultra-high temperature instantaneous steam sterilization device according to claim 3, characterized in that, In the method for obtaining the optimal equipment parameters, presetting a parameter range, where the parameter range includes a steam temperature range and a feeding speed range; randomly selecting a value from the steam temperature range and the feeding speed range respectively, and constructing a parameter set, a total of m parameter sets are constructed, and the m parameter sets are all different; The fitness difference f″ is obtained by calculating the difference between the fitness f′ corresponding to the new available solution χ′ and the fitness f corresponding to the available solution χ.

5. The intelligent control method of an ultra-high temperature instantaneous steam sterilization device according to claim 4, characterized in that, In the method for obtaining the optimal equipment parameters, the value of the fitness function is the residual contamination degree; The residual contamination degree is the average contamination degree of the microorganisms remaining after sterilization in the food sterilized in the same batch; the method for obtaining the residual contamination degree includes: Obtaining the sterilization distance, where the sterilization distance is the distance between the inlet and the outlet in the sterilization equipment; dividing the sterilization distance by the feeding speed corresponding to the available solution χ to obtain the sterilization duration; using the analysis data, the sterilization duration, and the steam temperature as test data, inputting the test data into the trained pollution prediction model to predict the corresponding residual contamination degree; the analysis data includes microbial contamination degree, moisture content, and food surface area.

6. The intelligent control method of an ultra-high temperature instantaneous steam sterilization device according to claim 5, characterized in that, The parameter influence data includes environmental influence data and power difference amount; the environmental influence data includes environmental temperature and environmental humidity; The method for obtaining the power difference amount is: continuously collecting the historical power difference amounts at c time points, where c is an integer greater than 1; training a difference prediction model according to the c historical power difference amounts; inputting the c historical power difference amounts into the trained difference prediction model to predict the power difference amount at the current time point.

7. The intelligent control method of an ultra-high temperature instantaneous steam sterilization device according to claim 6, characterized in that, The method for calculating the parameter deviation amount includes: Input the parameter influence data into the trained deviation analysis model to calculate the corresponding parameter deviation amount; the deviation analysis model is a deep neural network model; the parameter deviation amount is the steam temperature deviation amount. Add the parameter deviation amount to the steam temperature in the optimal equipment parameters to obtain the steam temperature correction amount, and correct the steam temperature in the optimal equipment parameters to the steam temperature correction amount.

8. The intelligent control method of an ultra-high temperature instantaneous steam sterilization device according to claim 7, characterized in that, The method for evaluating the sterilization effect of the food after sterilization includes: Collect the microbial contamination degree of the food after sterilization and label it as the remaining contamination degree; divide the remaining contamination degree by the microbial contamination degree to obtain the sterilization effect. The method for optimizing the preset feed rate according to the sterilization effect includes: The feed rate is the weight corresponding to the food sterilized in the same batch; preset an effect threshold, and compare the sterilization effect with the effect threshold; if the sterilization effect is less than the effect threshold, generate an optimization instruction; if the sterilization effect is greater than or equal to the effect threshold, do not generate an optimization instruction; preset a proportionality coefficient. If an optimization instruction is generated, multiply the proportionality coefficient by the sterilization effect to obtain the optimization ratio, and multiply the preset feed rate by the optimization ratio to obtain the optimized feed rate.

9. The intelligent control method of an ultra-high temperature instantaneous steam sterilization device according to claim 8, characterized in that, It also includes: Collect the distance to be sterilized and calculate the heating time, and adjust the feed rate according to the distance to be sterilized and the heating time. The distance to be sterilized is the distance between the food to be sterilized in the next batch and the entrance of the sterilization equipment. The method for calculating the heating time includes: Obtain the steam quality and the specific heat capacity of the steam; collect the current temperature of the steam; subtract the current temperature of the steam from the steam temperature in the optimal equipment parameters to obtain the temperature to be increased of the steam; obtain the actual heating power at the current time point and label it as the current power; multiply the steam quality, the specific heat capacity of the steam, and the temperature to be increased of the steam in sequence, and then divide by the current power to obtain the heating time. Divide the distance to be sterilized by the heating time to obtain the optimal feed rate; control the sterilization equipment to operate according to the optimal feed rate.

10. An intelligent control system for an ultra-high temperature instantaneous steam sterilization device, which implements the intelligent control method for an ultra-high temperature instantaneous steam sterilization device according to any one of claims 1-9, characterized in that, It includes: A data receiving module for receiving the food raw material data collected by the analysis terminal. A data analysis module for analyzing the food raw material data to obtain the food surface area. A parameter optimization module for optimizing the equipment parameters of the sterilization equipment according to the food raw material data and the food surface area to obtain the optimal equipment parameters. A data collection module for collecting parameter influence data. A parameter correction module for calculating the parameter deviation amount according to the parameter influence data, correcting the optimal equipment parameters according to the parameter deviation amount; and controlling the sterilization equipment to operate according to the corrected optimal equipment parameters. An effect evaluation module for evaluating the sterilization effect of the food after sterilization, optimizing the preset feed rate according to the sterilization effect, and sending the optimized feed rate to the analysis terminal.

Images